# Slack app

{% hint style="warning" %}
**Private preview.** This surface is not yet generally available. Adapters live in the Python SDK today and the rendering / configuration UX is under iteration. Contact <support@layerlens.ai> to request access to the private preview.
{% endhint %}

The Stratix Slack app routes notifications into a channel and supports a handful of quick actions from Slack itself.

## Install

From the Stratix Premium **Settings → Integrations → Slack**, click **Install**. You'll be redirected to Slack to authorize the app for your workspace and pick a channel.

## What it does

* **Routes notifications** — evaluation completions, threshold crossings, GEPA optimization completions, ECU low-balance warnings
* **Quick actions** from notification messages:
* Open the run in the Premium UI
* Acknowledge an alert
* Re-run a recurring trace evaluation
* **Search** — `/layerlens search...` from any channel

## Channel routing

Most orgs use one Slack channel for notifications. Per-event routing (e.g., billing notifications to a `#finance` channel; eval failures to `#oncall`) is configurable in **Settings → Notifications**.

## Permissions

The Slack app requests:

* **chat:write** — to post notification messages
* **commands** — to support the `/layerlens` slash command
* **users:read** — to map Slack users to Stratix users when applicable

## Where to next

* [Stratix Premium — Notifications](https://github.com/LayerLens/gitbook-full/blob/main/13-reference/sdk-python/notifications.md)
* [Settings](/11.-admin/settings.md)
* [Integrations](/6.-build-wire-your-code/migration.md)


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.layerlens.ai/6.-build-wire-your-code/slack.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.